Update code-review.md to avoid flagging test failures

Add explanatory-output-style and learning-output-style plugins to marketplace

.claude-plugin/marketplace.json

@@ -68,6 +68,28 @@
       },
       "source": "./plugins/code-review",
       "category": "productivity"
+    },
+    {
+      "name": "explanatory-output-style",
+      "description": "Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)",
+      "version": "1.0.0",
+      "author": {
+        "name": "Dickson Tsai",
+        "email": "dickson@anthropic.com"
+      },
+      "source": "./plugins/explanatory-output-style",
+      "category": "learning"
+    },
+    {
+      "name": "learning-output-style",
+      "description": "Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)",
+      "version": "1.0.0",
+      "author": {
+        "name": "Boris Cherny",
+        "email": "boris@anthropic.com"
+      },
+      "source": "./plugins/learning-output-style",
+      "category": "learning"
     }
   ]
 }

CHANGELOG.md

@@ -1,5 +1,39 @@
 # Changelog
 
+## 2.0.36
+
+- Fixed: DISABLE_AUTOUPDATER environment variable now properly disables package manager update notifications
+- Fixed queued messages being incorrectly executed as bash commands
+- Fixed input being lost when typing while a queued message is processed
+
+## 2.0.35
+
+- Improve fuzzy search results when searching commands
+- Improved VS Code extension to respect `chat.fontSize` and `chat.fontFamily` settings throughout the entire UI, and apply font changes immediately without requiring reload
+- Added `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` environment variable to automatically exit SDK mode after a specified idle duration, useful for automated workflows and scripts
+- Migrated `ignorePatterns` from project config to deny permissions in the localSettings.
+- Fixed messages returning null `stop_reason` and `stop_sequence` values
+- Fixed menu navigation getting stuck on items with empty string or other falsy values (e.g., in the `/hooks` menu)
+
+## 2.0.34
+
+- VSCode Extension: Added setting to configure the initial permission mode for new conversations
+- Improved file path suggestion performance with native Rust-based fuzzy finder
+- Fixed infinite token refresh loop that caused MCP servers with OAuth (e.g., Slack) to hang during connection
+- Fixed memory crash when reading or writing large files (especially base64-encoded images)
+
+## 2.0.33
+
+- Native binary installs now launch quicker.
+- Fixed `claude doctor` incorrectly detecting Homebrew vs npm-global installations by properly resolving symlinks
+- Fixed `claude mcp serve` exposing tools with incompatible outputSchemas
+
+## 2.0.32
+
+- Un-deprecate output styles based on community feedback
+- Added `companyAnnouncements` setting for displaying announcements on startup
+- Fixed hook progress messages not updating correctly during PostToolUse hook execution
+
 ## 2.0.31
 
 - Windows: native installation uses shift+tab as shortcut for mode switching, instead of alt+m

plugins/code-review/commands/code-review.md

@@ -31,7 +31,7 @@ Examples of false positives, for steps 4 and 5:
 - Pre-existing issues
 - Something that looks like a bug but is not actually a bug
 - Pedantic nitpicks that a senior engineer wouldn't call out
-- Issues that a linter will catch (no need to run the linter to verify)
+- Issues that a linter, typechecker, or test runner will catch (eg. failing tests, lint errors, type errors). Do not run these to verify; assume that they will be run as part of CI.
 - General code quality issues (eg. lack of test coverage, general security issues), unless explicitly required in CLAUDE.md
 - Issues that are called out in CLAUDE.md, but explicitly silenced in the code (eg. due to a lint ignore comment)